Tracking method and apparatus of landing goal of unmanned aerial vehicle, and unmanned aerial vehicle

Abstract

The invention discloses a tracking method and apparatus of a landing goal of an unmanned aerial vehicle, and the unmanned aerial vehicle. The method includes: determining a landing region and a position coordinate of the landing goal in a first frame of image according to YUV image data of the first frame of image including the landing goal, acquired by a camera of the unmanned aerial vehicle; extracting a first characteristic of the landing region; zooming the position coordinate of the landing region with a plurality of preset proportions to obtain a plurality of zoomed position coordinates,and regarding a plurality of regions determined by the plurality of zoomed position coordinates as a plurality of matching regions in a second frame of image, later acquired by the camera of the unmanned aerial vehicle; respectively extracting second characteristics of the plurality of matching regions, and determining the landing region and the position coordinate of the landing goal in the second frame of image according to the matching region corresponding to the second characteristic with the maximum matching degree with the first characteristic; and realizing tracking of the landing goal. According to the technical scheme, the marking accuracy of the tracking goal of the unmanned aerial vehicle is guaranteed, and the tracking efficiency and accuracy can be improved.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicles, in particular to a method and device for tracking a landing target of an unmanned aerial vehicle and an unmanned aerial vehicle. Background technique [0002] UAV tracking ground moving targets has important theoretical research significance and application value, and is an important research direction in the field of autonomous control of UAV systems. In the application of autonomous recognition and tracking of targets by UAVs, it is generally based on the images collected by the UAV camera, and by calculating the characteristics of the target in the image area, the marking of the target in the frame of the image is completed. When the frame image is correctly marked, the target tracking can be realized. For example, during the landing process of the UAV, it is necessary to accurately mark the landing target in order to accurately track the landing target, and finally realize th...

AI Technical Summary

Problems solved by technology

However, when the UAV is in the process of flying and tracking the target, the position of the target relative to the camera of the UAV changes. Accurate, so that tracking fails and reduces user experience

Images